Regression Techniques Research Articles

Exploring blood-brain barrier passage using atomic weighted vector and machine learning.

This study investigates the potential of leveraging molecular properties, as determined by MD-LOVIs software and machine learning techniques, to predict the ability of compounds to cross the blood-brain barrier (BBB). Accurate prediction of BBB permeation is critical for the development of central nervous system (CNS) drugs. The study applies various machine learning models, including both classification and regression techniques, to predict BBB passage and molecular activity. Notably, classification models such as GBM-AWV (accuracy = 0.801), GLM-CN (accuracy = 0.808), SVMPoly-means (accuracy = 0.980), SVMPoly-AC (accuracy = 0.980), SVMPoly-MI_TI_SI (accuracy = 0.900), SVMPoly-GI (accuracy = 0.900), RF-means (accuracy = 0.870), and GLM-means (accuracy = 0.818) demonstrate high accuracy in predicting BBB passage. In contrast, regression models like ES-RLM-AG (R2 = 0.902), IB-IBK (R2 = 0.82), IB-Kstar (R2 = 0.834), IB-MLP (R2 = 0.843), and DRF-AWV (R2 = 0.810) exhibit strong performance in predicting molecular activity. The results show that classification models like GBM-AWV, GLM-CN, and SVMPoly variants, as well as regression models like ES-RLM-AG and IB-MLP, achieve high performance, demonstrating the effectiveness of machine learning in predicting BBB permeability. The computational methods employed in this study include the MD-LOVIs software for generating molecular descriptors and several machine learning algorithms, including gradient boosting machines (GBM), generalized linear models (GLM), support vector machines (SVM) with polynomial kernels, random forests (RF), ensemble regression models, and instance-based learning algorithms. These models were trained and validated using various datasets to predict BBB passage and molecular activity, with the performance metrics reported for each model. Standard computational techniques were employed throughout, ensuring the reliability of the predictions.

Strategy towards sustainable energy transition: The effect of policy uncertainty, environmental technology and natural resources rent in the OECD nations

The stupendous increase in environmental pollutants alongside climate alterations are calling for integrated tasks at the global level to meet the Paris Agreements. Energy conversion from fossil fuel to renewable energy sources is an important step to address the adverse effects of extreme climatic conditions. This study explores the key contributors of energy transition in the context of the OECD countries during the period 1991 to 2019. To this end the major determinants chosen include natural resources rents, policy uncertainty, environmental technologies, environmental policies, income and globalization. The quantile regression technique is used to explore heterogeneous role of the contributory factors of energy transition across its different levels. This study applies method of moments quantile regression (hereafter MM-QR) by Machado and Silva (2019) that provides evidence on how the covariates affect the integral conditional distributions of energy transition. The study documents interesting findings. (i) Natural resources rents reduce the pace of the progress of sustainable energy transition in OECD economies. (ii) An escalation in the world uncertainty index leads to an improvement in energy transition index. (iii) Environmental technologies support the transition concerning cleaner and more efficient energy sources. (iv) Finally, as natural resources, uncertainty, environmental technologies, and globalization impacts energy transition differently, their effects need to be rationalized with varying environmental policy instruments. The study concludes that energy transition process requires the task of upgrading the quality of implementation of policies related to energy technology.

Hedge Accounting Disclosures and Sustainable Growth of Listed Deposit Money Banks in Nigeria

The primary problem facing listed deposit money banks in Nigeria is their struggle to achieve sustainable growth in a volatile economic environment. This study investigated the impact of hedge accounting disclosures on the sustainable growth of these banks, focusing on commodity hedge disclosure, interest rate hedge disclosure, and foreign exchange rate disclosure, while controlling for market capitalization. Using an ex post facto research design, the study analyzed secondary data from 11 selected banks over a period of 10 years from 2014 to 2023. The method of data analysis was random effect regression technique. The findings revealed that commodity hedge disclosure (COMD) and interest rate hedge disclosure (INTD) have significant positive effects on the sustainable growth rates of listed deposit money banks in Nigeria. Conversely, foreign exchange rate disclosure (FEXD) has a significant negative effect on sustainable growth, indicating that high levels of foreign exchange risk exposure, when disclosed, may reduce investor confidence and perceived stability. The study concluded that hedge accounting disclosures significantly impact sustainable growth of listed deposit money banks in Nigeria. It recommended the management of listed deposit money banks in Nigeria should enhance commodity and interest rate hedge disclosures to improve the quality of foreign exchange risk communication.

The government's environmental attention and corporate green innovation: A threshold analysis and quantile regression approach.

Based on an analysis of 643 listed firms in clean technology sectors, this study explores the nonlinear impact of the government's environmental attention (GEA) on firms' green innovation by exploiting threshold and quantile regression techniques on Stata 17. We show that a double threshold exists when the level of the GEA is 51 or 104, above which the positive impact of the GEA on green innovation in cleantech firms significantly diminishes. The results from the quantile regression further indicate that cleantech firms receive almost no benefits from the GEA at lower levels of green innovation. Thus, policy-makers designing environmental policies should consider that the marginal benefit of environmental attention on green innovation wanes beyond certain levels, especially for firms that lack sufficient enthusiasm for innovation.

Statistical Relationship between Satellite observed Land Surface Temperature and in-situ measured Surface Air Temperature over the Indian Region: An Exploratory Study

This paper presents an investigation of spatio-temporal estimation of daily minimum (Tmin) and maximum (Tmax) surface air temperature using satellite (INSAT and MODIS) derived Land surface temperature and in-situ observational data over the Indian region. Least Absolute Shrinkage and Selection Operator (LASSO) regression technique is used to identify influencing neighboring stations. To capture spatial and temporal variability of surface air temperature of a particular IMD station, Linear Regression and Auto-Regressive Integrated Moving Average, which is known as ARIMA, are used respectively. These models are statistically ensembled using stack generalization. Obtained station-by-station relationship is validated on an independent test data using Root Mean Squared Error (RMSE) to check the validity of the model under consideration. Results show ensembled model outperform (has lowest RMSE) the traditional methods for prediction of Tmin and Tmax with RMSE within a range of [1, 2] range for most of the regions and seasons.

Challenges and Techniques in Multilingual Fake News Detection

The spread of false information across language and cultural barriers poses a significant threat to global societies. This study investigates the obstacles in detecting misinformation in various languages, including linguistic diversity, limited datasets, cultural nuances, and the ever- changing strategies of disinformation propagators. These complex issues require advanced methods to effectively identify and combat false information across multiple languages. The research evaluates several prominent machine learning approaches, such as Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Logistic Regression, Decision Trees, and Natural Language Processing (NLP) techniques. By examining their effectiveness in multilingual contexts, this study sheds light on the advantages and drawbacks of each method. It underscores the need for continuous innovation and collaborative efforts in developing robust detection systems that can adapt to the ever-changing landscape of misinformation. These initiatives aim to promote informed public discourse and improve information integrity across diverse cultural contexts. Key Words: Multilingual Fake News Detection, Machine Learning, Machine Learning algorithms, Natural Language Processing, Misinformation.

A bayesian shared component spatial modeling approach for identifying the geographic pattern of local associations: a case study of young offenders and violent crimes in Greater Toronto Area

Background settingTraditional spatial or non-spatial regression techniques require individual variables to be defined as dependent and independent variables, often assuming a unidirectional and (global) linear relationship between the variables under study. This research studies the Bayesian shared component spatial (BSCS) modeling as an alternative approach to identifying local associations between two or more variables and their spatial patterns.MethodsThe variables to be studied, young offenders (YO) and violent crimes (VC), are treated as (multiple) outcomes in the BSCS model. Separate non-BSCS models that treat YO as the outcome variable and VC as the independent variable have also been developed. Results are compared in terms of model fit, risk estimates, and identification of hotspot areas.ResultsCompared to the traditional non-BSCS models, the BSCS models fitted the data better and identified a strong spatial association between YO and VC. Using the BSCS technique allowed both the YO and VC to be modeled as outcome variables, assuming common data-generating processes that are influenced by a set of socioeconomic covariates. The BSCS technique offered smooth and easy mapping of the identified association, with the maps displaying the common (shared) and separate (individual) hotspots of YO and VC.ConclusionsThe proposed method can transform existing association analyses from methods requiring inputs as dependent and independent variables to outcome variables only and shift the reliance on regression coefficients to probability risk maps for characterizing (local) associations between the outcomes.

Drug use and divorce rates in Bayelsa State, Nigeria

This study examines the relaonship between drug use and divorce rates in Bayelsa State Nigeria, it ulized survey design, using quesonnaire to obtain data with a purposive sample size of 420. The data was analyzed using the Logisc and the Probit regression techniques. It was found that drug consumpon, frequency of drug consumpon and misuse of drug had a posive and insignificant impact on divorce among drug consumers. 2 The Pseudo R presented in column (1) shows that the variables in the model explain approximately 68.56% change in the divorce rate. The likelihood chi-square value of 30.53 (p = 0.0000) means that the variables jointly significantly affect the rate of divorce. The pvalue for hats is 0.239. The non-significant hatsq means good regression model adequacy. Also, the insignificant Hosmer-Lemeshow goodness of fit test is evidence of the overall goodness of fit of the regression model. Sensizaon of the dangers associated with the abuse of drug, frequent consumpon of drug and the use of drug without a medical doctor's prescripon is recommended.

The Effect of Digital Literacy, Technological Adoption, and Collaborative Learning on Student Engagement in Business Education

This study explores the influence of digital literacy, technological adoption, and collaborative learning on student engagement in business education. Utilizing a quantitative research design, data were collected from 300 undergraduate students enrolled in business programs through a structured questionnaire. The analysis employed descriptive statistics, correlation analysis, and multiple regression techniques to investigate the relationships between the variables. The results revealed that digital literacy, technological adoption, and collaborative learning significantly contribute to student engagement, with collaborative learning emerging as the strongest predictor. The findings underscore the importance of enhancing digital literacy and promoting technology use in educational settings, alongside fostering collaborative learning experiences, to improve student engagement in business education. These insights have implications for educators and curriculum designers seeking to create more effective and engaging learning environments.

Enhancing Prediction of Human Traits and Behaviors through Ensemble Learning of Traditional and Novel Resting-State fMRI Connectivity Analyses.

Recent advances in cognitive neuroscience have focused on using resting-state functional connectivity (RSFC) data from fMRI scans to more accurately predict human traits and behaviors. Traditional approaches generally analyze RSFC by correlating averaged time-series data across regions of interest (ROIs) or networks, which may overlook important spatial signal patterns. To address this limitation, we introduced a novel linear regression technique that estimates RSFC by predicting spatial brain activity patterns in a target ROI from those in a seed ROI. We applied both traditional and our novel RSFC estimation methods to a large-scale dataset from the Human Connectome Project and the Brain Genomics Superstruct Project, analyzing resting-state fMRI data to predict sex, age, personality traits, and psychological task performance. To enhance prediction accuracy, we developed an ensemble learner that combines these qualitatively different methods using a weighted average approach. Our findings revealed that hierarchical clustering of RSFC patterns using our novel method displays distinct whole-brain grouping patterns compared to the traditional approach. Importantly, the ensemble model, integrating these diverse weak learners, outperformed the traditional RSFC method in predicting human traits and behaviors. Notably, the predictions from the traditional and novel methods showed relatively low similarity, indicating that our novel approach captures unique and previously undetected information about human traits and behaviors through fine-grained local spatial patterns of neural activation. These results highlight the potential of combining traditional and innovative RSFC analysis techniques to enrich our understanding of the neural basis of human traits and behaviors.

Urban Heat Island and Environmental Degradation Analysis Utilizing a Remote Sensing Technique in Rapidly Urbanizing South Asian Cities

Rapid urbanization in South Asian cities has triggered significant changes in land use and land cover (LULC), degrading natural biophysical components and intensifying urban heat islands (UHIs). This study investigated the impact of LULC changes on land surface temperature (LST) and the role of biophysical indicators in enhancing urban resilience to thermal extremes. We used Landsat satellite imageries from 1993 to 2023, conducted a comprehensive analysis of LULC changes, and estimated LST variations at 6-year intervals in the Dhaka, Gazipur, and Narayanganj districts in Bangladesh. Afterward, we performed statistical analysis upon employing correlation, regression, and principal component analysis (PCA) techniques to summarize information. The results reveal that 339.13 km2 worth of urban expansion has occurred in last 30 years, with an average annual growth rate of 3.5%, accompanied by a substantial reduction in water bodies (−139.17 km2) and vegetation cover. Consequently, summer temperatures exceeded approximately 36.52 °C in dense urban areas. Also, the results highlighted the strong influence of built-up areas (BSI and SAVI) on LST, while vegetation (NDVI) and water indices (NDWI) exhibited a negative association. The findings emphasize the urgency of integrating green infrastructure and deploying sustainable urban planning policies to mitigate the potential adverse impacts of scattered urbanization in the face of climate change.

In‐Silico Design of Novel Indole‐Selenide Derivatives as Potential P‐Glycoprotein Inhibitors Against Multi‐Drug Resistance in MCF‐7/ADR Cells: 2D‐QSAR, Molecular Docking, and Dynamics Simulations

AbstractIn this work, a set of thirty‐one novel indole‐selenide derivatives (C1–C31), reported recently as P‐glycoprotein inhibitors against multi‐drug resistance in MCF‐7/ADR cells, have been computationally investigated for the first time by in‐silico approaches, combining 2D‐quantitative structure‐activity relationship based virtual screening (2D‐QSAR‐VS) model, molecular docking, and dynamics simulations. The in‐silico study aims to design new potent molecules with higher anticancer inhibitory activity than observed with in‐vitro assays. The 2D‐QSAR model is built using multiple linear regression (MLR) techniques, and cross‐validated by internal and external parameters, applicability domain (AD) analysis, and Y‐randomization tests, corroborating the Golbreikh and Tropsha criteria. Subsequently, virtual screening was performed on the generated database, considering higher pIC50 values than the most effective in‐vivo C27 inhibitor. Subsequently, molecular docking and dynamics simulations were applied on the selected higher‐scoring ligands showing the best interactions with the PHE643, TYR745, and PRO571 amino acids of the P‐gp receptor (7 A6E), predicting dynamically stable complexes at the time‐scale of 200 ns. The in‐silico outcomes indicate that the selected new ligands have shown promising inhibitory activity for future anti‐cancer therapies, with perspective validating by in‐vitro and in‐vivo studies.

Examining Cycle Threshold values in Repeat SARS-CoV-2 Cases: A Retrospective Analysis in Ireland

Abstract Background Effective public health management during the COVID-19 pandemic requires accurate differentiation between re-infections and residual viral RNA detections in repeat positive cases. This study investigates cycle threshold (CT) trends in repeat SARS-CoV-2 cases to discern between persistent viral remnants and active infections. Collaboration between contact tracing and laboratories is essential for shaping robust public health strategies. Methods A retrospective analysis was conducted on 427 individuals with repeat positive PCR tests. Data was collected at a contact tracing centre from March to August 2021. Key variables including age, gender, and biomedical markers (test intervals, CT values) were examined. Regression and correlation techniques assessed CT trends and their implications. Results Younger individuals (<60 years) occasionally exhibited significantly lower CT values in subsequent tests, suggesting potential re-infections, while older adults generally displayed higher CT values indicative of residual RNA. These age-specific CT trends were statistically significant and instrumental in refining testing protocols and isolation guidelines. Further analysis is expected to strengthen these findings Conclusions Collaborative approaches between contact tracing and laboratories are vital in shaping robust public health strategies for distinguishing between types of repeat infections. Revision of health policies is imperative to prevent unnecessary isolation and optimise healthcare workforce allocation during ongoing transmission periods. Key messages • Decisive decision-making skills are crucial in managing repeat SARS-CoV-2 infections. • Revised health policies align testing and isolation practices with empirical CT data, enhancing public health efficacy.

How to prevent suicidal behavior and non-suicidal self-injury? An analysis of adolescent typologies

Non-suicidal self-injury (NSSI) and suicidal behavior in adolescence are global mental health concerns. These behaviors are often interconnected, but can also manifest independently. This study aimed to assess the predictive abilities of neuroticism, emotional competencies, and the school social climate on four typologies based on the presence of NSSI and levels of suicidal behavior. The study included 713 participants aged 11–16 years who completed questionnaires assessing suicidal behavior, NSSI, neuroticism, emotional competencies, and the school social climate. The data were analyzed using logistic regression techniques. The findings revealed that adolescents with high levels of neuroticism and emotion perception, low levels of emotion expression and regulation and an inadequate school social climate were more likely to belong to typologies characterized by NSSI and/or high suicidal behavior. This study underscores the importance of enhancing the school social climate as a crucial step toward reducing the likelihood of NSSI and suicidal behavior.

The Influence of Emotional Instability on Weight Fluctuations

This study examines the relationships between psychological factors, specifically mood fluctuations, short temper, and feelings of negativity, and their impact on weight gain or loss among individuals. The objective is to determine how these emotional states individually and collectively influence weight changes, focusing on understanding their predictive power. A quantitative, cross-sectional design was employed. The analysis involved correlation and multiple regression techniques to explore the relationships between the variables. Results revealed that moodiness has the strongest positive correlation with weight changes and is the most significant predictor, explaining a substantial portion of the variance. Short temper and feelings of negativity also contributed to body weight variations, though to a lesser extent. The model explained the variance in weight outcomes, highlighting the meaningful role of psychological factors in weight management. This study contributes to the growing body of research emphasizing the need to integrate mental health support in weight management programs and policy interventions, recognizing the critical role of mental well-being in influencing physical outcomes such as weight fluctuations. The findings have important implications for healthcare providers, policymakers, and wellness programs aiming to address health's psychological and physical aspects.

Machine Learning techniques for predicting inpatient probability and LOS from EU Injury Database

Abstract Background Unlike statistical inference Machine Learning (ML) makes repeatable predictions without prior assumptions about the underlying relationships among variables. The Full Data Set (FDS) of the EU-IDB (European Injury DataBase) consent to explore risk of hospitalization due to injuries using many predictors. The Length Of Stay of patients in hospital (LOS) is a relevant proxy of complexity of treatment and resources consumption. Methods The IDB-FDS provides more than 3.800.000 ED records, in years 2008-19 for 19 Countries. LASSO (Least Absolute Shrinkage and Selection Operator) cross-validated linearized regression technique (linear for LOS) was used for variable selection and parameter regularization. Inpatients are those admitted or transferred to hospital. Days of hospitalization were used for LOS. A cross-validated Generalized Linear Model was performed on 5 folds randomly sampled assigning 80% of records to training and 20% to testing samples. Results The strongest predictors of hospital admission risk, selected by the model were in order of importance: EUROCOST-39 diagnoses categories, Age Group, Intent, Mechanism Of Injury, Activity When Injured, Transport Injury Event, Sex Of Patient, Place Of Occurrence. EUROCOST-39 represents 61,9% of explained variability and age group 19,4%. The strongest predictors of LOS were substantially the same: EUROCOST-39 86,2% of explained variability and age group 8,6%. Conclusions The main part of variability in the ML model is explained by diagnoses reclassified according to a disability standardization method. For instance, in the maximum training sample risk of hospitalization ranges from odd 0,76% for hand/fingers sprain up to 154,02% for brain concussion. In the median sample LOS ranges from 0,45 days for strain of hand/fingers up to 11,65 for multi-trauma. A combination of more disabling injury, older age and mechanism of injury (i.e. threat to breathing) increases enormously the risk of hospitalization and LOS. Key messages • Machine Learning techniques applied on EU-IDB can provide identification of relevant risk factors of hospital admission from injuries for targeting preventive measures and organizing health care. • Artificial Intelligence consents to analyse big amount of data as dimension or analytical detail of information for identifying patterns and predictors of specific indicators for injuries or diseases.

Understanding the Impact of Social and Facilitating Factors on Drone Adoption in the Takaful Sector of Malaysia and Indonesia

The takaful industry, a sector that is guided by Shariah-compliant principles, is progressively investigating cutting-edge technologies to improve service delivery and operational efficiency. This study investigates the influence of social factors and facilitating conditions on the intention to adopt drone technology within the Takaful sector in Malaysia and Indonesia. A quantitative research design was employed, with data collected from 68 Takaful professionals. The results were analyzed using correlation and regression techniques. The findings revealed that social influence and facilitating conditions significantly impact behavior intention, while performance and effort expectancy were found to be less important. Additionally, the study integrates Maqasid Shariah principles, ensuring that the adoption of drone technology aligns with Islamic ethical considerations. The study also urges more investigation to investigate the generalisability of these results over many cultural and legal environments as well as the possible impact of developing technologies like artificial intelligence and blockchain on the sector.

Assessing the Financial Impact of CSR Initiatives in Indian IT Companies

Corporate Social Responsibility (CSR) is increasingly recognized as a vital component of modern business strategy, particularly in the IT sector. CSR initiatives reflect a company’s commitment to ethical practices, environmental sustainability, and social welfare, thereby enhancing its reputation and stakeholder trust. This study explores the financial health and the impact of CSR on the financial performance of Tata Consultancy Services Limited (TCS) and Infosys Limited over a five-year period from 2018-19 to 2022-23. In this study ratio analysis and regression techniques have been used to analyses the financial health of these leading IT companies and examining the impact of CSR spending on financial performance such as net profit margins and Return on Assets (ROA). The comparative analysis highlights that while both companies have shown a strong commitment to CSR, there is no direct impact of CSR spending on their net profit margins or ROA. TCS has consistently demonstrated higher CSR spending, net profit margins, and ROA compared to Infosys, reflecting superior financial management and asset utilization. This study underscores the importance of CSR as a strategic component for reputation and sustainability, even though its direct financial impact remains indeterminate.

Personal Bankruptcy Prediction Using Logistic Regression Model

According to the Insolvency Department of Malaysia, as of December 2023, 233,483 Malaysians are currently involved in bankruptcy cases due to their defaults on hire purchase loans, credit card loans, personal loans, housing loans, and business loans. This is indeed a critical issue because the growing number of personal bankruptcy cases will hurt the Malaysian economy as well as society. From an individual's economic perspective, bankruptcy minimizes their chances of getting a job. Apart from that, their accounts will be frozen, they will lose control of their properties and assets, and they will not be allowed to start any business or be a part of any company's Board of Directors. Bankrupts also will be rejected from any loan application. This paper examines this problem by developing a personal bankruptcy prediction model using the logistic regression technique. This paper defines "bankrupt" as terminated members who failed to settle their loans. The sample comprised 24,546 cases with 17% settled cases and 83% terminated cases. The data included a dependent variable, i.e., bankruptcy status (Y=1(bankrupt), Y=0(non-bankrupt)), and 12 predictors. Upon completion, this paper succeeds in coming out with a reliable personal bankruptcy prediction model and significant variables of personal bankruptcy. The findings of this paper are very beneficial and significant to creditors, banks, the Malaysia Department of Insolvency, potential borrowers, members of AKPK, and society in general in raising awareness of personal bankruptcy risks and such information may help them to take preventive measures in minimizing the number of personal bankruptcy cases.

Quantitative evidence of the community of shared future for mankind as a driver of sustainable development in human society

In an era marked by global economic challenges, an increasing array of non-traditional security threats, and a proliferation of conflicts and issues, China has put forth the building of a community of shared future for mankind as a way to address this question of the times. The theory of the community of shared future for mankind offers a framework to address contemporary issues by promoting equality, mutual benefit, security, justice, openness, innovation, multicultural exchange, and green development. This paper innovatively quantifies the five core principles of the theory of the community of shared future for mankind using the entropy method. It calculates the proxy variable for sustainable development, green total factor productivity, using the super-efficiency Slack-Based Measure model in Data Envelopment Analysis. Baseline regression is conducted on this basis. The Principal Component Analysis method and another Data Envelopment Analysis method, the Malmquist index, are utilized to recalculate the indicators, followed by another round of regression analysis. The results are consistent with the baseline regression. Additionally, Ordinary Least Squares, Partial Least Squares, Maximum Likelihood Estimation, Ridge regression, and Lasso regression are employed to ensure the robustness of the results. The findings indicate a significant positive relationship between the community of a shared future for mankind and the sustainable development of human society, with consistent conclusions drawn from different calculation methods and regression techniques. Through value recognition, international cooperation based on benefit-sharing and mutual reciprocity can guide humanity towards a harmonious coexistence with nature, irrespective of regional and economic disparities. This study provides quantitative evidence of the impact of the community of a shared future for mankind on the sustainable development of human society, filling a gap in existing research. Based on these findings, feasible policy recommendations are proposed to promote sustainable development in human society.